{"id":21889716,"url":"https://github.com/annndruha/ocr-munji","last_synced_at":"2025-07-21T10:31:24.170Z","repository":{"id":65559383,"uuid":"594535130","full_name":"annndruha/OCR-Munji","owner":"annndruha","description":"Text detection of printed text in Munji language.","archived":true,"fork":false,"pushed_at":"2023-02-13T22:42:52.000Z","size":9674,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-22T02:42:26.313Z","etag":null,"topics":["lingustics","ocr","ocr-python","ocr-recognition"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/annndruha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-01-28T21:03:05.000Z","updated_at":"2023-09-30T14:23:28.000Z","dependencies_parsed_at":"2023-02-15T23:31:14.562Z","dependency_job_id":null,"html_url":"https://github.com/annndruha/OCR-Munji","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/annndruha/OCR-Munji","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/annndruha%2FOCR-Munji","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/annndruha%2FOCR-Munji/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/annndruha%2FOCR-Munji/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/annndruha%2FOCR-Munji/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/annndruha","download_url":"https://codeload.github.com/annndruha/OCR-Munji/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/annndruha%2FOCR-Munji/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266285132,"owners_count":23905271,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["lingustics","ocr","ocr-python","ocr-recognition"],"created_at":"2024-11-28T11:26:36.168Z","updated_at":"2025-07-21T10:31:23.392Z","avatar_url":"https://github.com/annndruha.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## OCR-Munji\n\nMunji language text detection.\n\nDetector created for book \"Грюнберг А.Л. — Мунджанский язык Тексты\" with printed text.\n\n![readme.png](readme.png)\n\n### Alghoritm\n\nThe detector is based on Google cloud vision text detection with additional heuristics that recognize the characters of Munji language. A variety of heuristics are used, such as the correlation of special characters or signs and the replacement of some letters obtained by Google text detection. (See `detector/mapping.py`)\n\n\n### Using \n\n#### Step 0\nInstall requirements\n\n```commandline\npip install -r requirements.txt\n```\n\n#### Step 1\n\nFor use Google cloud vision you need to get [GOOGLE_APPLICATION_CREDENTIALS](https://cloud.google.com/vision/docs/detect-labels-image-client-libraries#before-you-begin) and set corresponding environment variable.\n\n#### Step 2\n\nGet Google cloud vision text detection response for image:\n```commandline\npython detector\\google_ocr.py --path tests/page148/img.png\n```\nIf command succeed, response saved as `.pickle` file.\n\n#### Step 3\n\nGet Munji text from image and google response:\n\n```commandline\npython -m detector tests/page148/img.png tests/page148/img.pickle\n```\n\nor simply\n```commandline\npython -m detector tests/page148/img.png\n```\nif response located in same dirictory with same filename as image.\n\n**Result**\n\nResulted detected text located in `.txt`-file near `.pickle`-file.\n\n### Tested on\n|                  | version  |\n|------------------|----------|\n| Windows          | 11       |\n| Python           | 3.11     |\n| pip              | 23.0     |\n| numpy            | 1.24.1   |\n| opencv-python    | 4.7.0.68 |\n| google           | 3.0.0    |\n| google-cloud-vision | 3.3.1    |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fannndruha%2Focr-munji","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fannndruha%2Focr-munji","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fannndruha%2Focr-munji/lists"}